Predicting Drug-Drug Interactions Using Knowledge Graphs

TL;DR

This paper introduces medicX, a framework that leverages knowledge graphs and advanced embedding techniques to predict drug-drug interactions with high accuracy, outperforming existing models.

Contribution

The paper presents a novel end-to-end framework combining multiple drug features into a knowledge graph and applying various embedding methods, including GNNs, for improved DDI prediction.

Findings

ComplEx + LSTM achieved 95.19% F1-score, outperforming DeepDDI.

GNN-based auto-encoder achieved 91.94% F1-score, showing strong semantic mining.

Higher dimension embeddings in GNNs can further enhance performance.

Abstract

In the last decades, people have been consuming and combining more drugs than before, increasing the number of Drug-Drug Interactions (DDIs). To predict unknown DDIs, recently, studies started incorporating Knowledge Graphs (KGs) since they are able to capture the relationships among entities providing better drug representations than using a single drug property. In this paper, we propose the medicX end-to-end framework that integrates several drug features from public drug repositories into a KG and embeds the nodes in the graph using various translation, factorisation and Neural Network (NN) based KG Embedding (KGE) methods. Ultimately, we use a Machine Learning (ML) algorithm that predicts unknown DDIs. Among the different translation and factorisation-based KGE models, we found that the best performing combination was the ComplEx embedding method with a Long Short-Term Memory (LSTM) network, which obtained an F1-score of 95.19% on a dataset based on the DDIs found in DrugBank version 5.1.8. This score is 5.61% better than the state-of-the-art model DeepDDI. Additionally, we also developed a graph auto-encoder model that uses a Graph Neural Network (GNN), which achieved an F1-score of 91.94%. Consequently, GNNs have demonstrated a stronger ability to mine the underlying semantics of the KG than the ComplEx model, and thus using higher dimension embeddings within the GNN can lead to state-of-the-art performance.